*Memos:
- My post explains OxfordIIITPet().
RandomResizedCrop() can crop a random part of an image, then resize it to a given size as shown below:
*Memos:
- The 1st argument for initialization is
size(Required-Type:intortuple/list(int) or size()):
*Memos:- It’s
[height, width]. - It must be
1 <= x. - A tuple/list must be the 1D with 1 or 2 elements.
- A single value(
intortuple/list(int)) means[size, size].
- It’s
- The 2nd argument for initialization is
scale(Optional-Type:tuple/list(intorfloat)):
*Memos:- It's
[min, max]so it mustmin <= max. - It must be
0 <= x. - A tuple/list must be the 1D with 2 elements.
- A double of
0or1 <= xgets the same result.
- It's
- The 3rd argument for initialization is
ratio(Optional-Type:tuple/list(intorfloat)):
*Memos:- It's
[min, max]so it mustmin <= max. - It must be
0 < x. - A tuple/list must be the 1D with 2 elements.
- It's
- The 4th argument for initialization is
interpolation(Optional-Default:InterpolationMode.BILINEAR-Type:InterpolationMode). - The 5th argument for initialization is
antialias(Optional-Default:True-Type:bool). *Even if settingFalseto it, it's alwaysTrueifinterpolationisInterpolationMode.BILINEARorInterpolationMode.BICUBIC. - The 1st argument is
img(Required-Type:PIL Imageortensor(int)):
*Memos:- A tensor must be 3D.
- Don't use
img=.
-
v2is recommended to use according to V1 or V2? Which one should I use?.
from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import RandomResizedCrop
from torchvision.transforms.functional import InterpolationMode
rrc = RandomResizedCrop(size=100)
rrc = RandomResizedCrop(size=100,
scale=(0.08, 1.0),
ratio=(0.75, 1.3333333333333333),
interpolation=InterpolationMode.BILINEAR,
antialias=True)
rrc
# RandomResizedCrop(size=(100, 100),
# scale=(0.08, 1.0),
# ratio=(0.75, 1.3333333333333333),
# interpolation=InterpolationMode.BILINEAR,
# antialias=True)
rrc.size
# (100, 100)
rrc.scale
# (0.08, 1.0)
rrc.ratio
# (0.75, 1.3333333333333333)
rrc.interpolationa
#
rrc.antialias
# True
origin_data = OxfordIIITPet(
root="data",
transform=None
)
s1000_data = OxfordIIITPet( # `s` is size.
root="data",
transform=RandomResizedCrop(size=1000)
# transform=RandomResizedCrop(size=[1000])
# transform=RandomResizedCrop(size=[1000, 1000])
)
s500_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=500)
)
s100_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=100)
)
s50_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=50)
)
s10_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=10)
)
s1_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=1)
)
s600_900_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=[600, 900])
)
s900_600_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=[900, 600])
)
s200_300_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=[200, 300])
)
s300_200_data = OxfordIIITPet(
root="data",
transform=RandomResizedCrop(size=[300, 200])
)
import matplotlib.pyplot as plt
def show_images1(data, main_title=None):
plt.figure(figsize=[10, 5])
plt.suptitle(t=main_title, y=0.8, fontsize=14)
for i, (im, _) in zip(range(1, 6), data):
plt.subplot(1, 5, i)
plt.imshow(X=im)
plt.tight_layout()
plt.show()
show_images1(data=origin_data, main_title="origin_data")
show_images1(data=s1000_data, main_title="s1000_data")
show_images1(data=s500_data, main_title="s500_data")
show_images1(data=s100_data, main_title="s100_data")
show_images1(data=s50_data, main_title="s50_data")
show_images1(data=s10_data, main_title="s10_data")
show_images1(data=s1_data, main_title="s1_data")
print()
show_images1(data=origin_data, main_title="origin_data")
show_images1(data=s600_900_data, main_title="s600_900_data")
show_images1(data=s900_600_data, main_title="s900_600_data")
show_images1(data=s200_300_data, main_title="s200_300_data")
show_images1(data=s300_200_data, main_title="s300_200_data")
# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, s=None, sc=(0.08, 1.0),
r=(0.75, 1.3333333333333333),
ip=InterpolationMode.BILINEAR, a=True):
plt.figure(figsize=[10, 5])
plt.suptitle(t=main_title, y=0.8, fontsize=14)
for i, (im, _) in zip(range(1, 6), data):
plt.subplot(1, 5, i)
if s:
rrc = RandomResizedCrop(size=s, scale=sc, # Here
ratio=r, interpolation=ip,
antialias=a)
plt.imshow(X=rrc(im)) # Here
else:
plt.imshow(X=im)
plt.tight_layout()
plt.show()
show_images2(data=origin_data, main_title="origin_data")
show_images2(data=origin_data, main_title="s1000_data", s=1000)
show_images2(data=origin_data, main_title="s500_data", s=500)
show_images2(data=origin_data, main_title="s100_data", s=100)
show_images2(data=origin_data, main_title="s50_data", s=50)
show_images2(data=origin_data, main_title="s10_data", s=10)
show_images2(data=origin_data, main_title="s1_data", s=1)
print()
show_images2(data=origin_data, main_title="origin_data")
show_images2(data=origin_data, main_title="s600_900_data", s=[600, 900])
show_images2(data=origin_data, main_title="s900_600_data", s=[900, 600])
show_images2(data=origin_data, main_title="s200_300_data", s=[200, 300])
show_images2(data=origin_data, main_title="s300_200_data", s=[300, 200])
